{"id":"W4414978537","doi":"10.1145/3763128","title":"TraceLinking Implementations with Their Verified Designs","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"TRACE (psycholinguistics); Compiler; Correctness; Modular design; Tracing; Verifiable secret sharing; Debugging; Semantics (computer science); Implementation; Signature (topology)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01078401,0.001313285,0.0008189958,0.001950088,0.0009688811,0.00645932,0.002819241,0.00244446,0.01004142],"category_scores_gemma":[0.06727486,0.001792199,0.001690862,0.001162549,0.003375852,0.006404376,0.003996609,0.003323928,0.002195815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002349553,"about_ca_system_score_gemma":0.005990205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002553693,"about_ca_topic_score_gemma":0.002161457,"domain_scores_codex":[0.9797367,0.007339109,0.002408217,0.001782935,0.00789353,0.0008394877],"domain_scores_gemma":[0.9508989,0.01773638,0.004451578,0.01995615,0.006648906,0.0003080483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005830546,0.0005757029,0.007892069,0.002008096,0.0002421668,0.001621558,0.004514406,0.1292206,0.03411638,0.4223217,0.007035298,0.389869],"study_design_scores_gemma":[0.0004642275,0.0005304783,0.001478117,0.001276335,0.0002854644,0.0008525091,0.001112465,0.4290352,0.1434738,0.3032784,0.1179456,0.0002673564],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01433323,0.00008767582,0.9723738,0.0002850093,0.0001135667,0.0003155921,0.0001896302,0.00809368,0.004207848],"genre_scores_gemma":[0.1921308,0.0003464519,0.7958923,0.0003107693,0.00005143848,0.001033735,0.0007452024,0.003592364,0.005896917],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01078401,"threshold_uncertainty_score":0.05703199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03409471806375904,"score_gpt":0.3255725245977236,"score_spread":0.2914778065339646,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}